Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    biographical details and achievements of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    introducing people or listing attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ̙
    -0.37
     Fama
    -0.35
    xes
    -0.34
    ("")]
    -0.34
    ACHUSET
    -0.33
     falso
    -0.32
    TokenNameLBRACE
    -0.32
    BIP
    -0.32
    兮
    -0.31
     kontro
    -0.31
    POSITIVE LOGITS
    ConstraintMaker
    0.60
     nakalista
    0.57
     defaultstate
    0.55
    styleType
    0.54
     wonderful
    0.52
    appartamento
    0.50
     delightful
    0.49
    writeHead
    0.48
    wonderful
    0.48
     Comprometido
    0.47
    Act Density 0.015%

    No Known Activations